Geekbench AI Score

399
Single Precision Score
4128
Half Precision Score
7075
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

User ronitroyri
Upload Date August 31 2025 03:36 AM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device Google Tensor G3
System Information
Operating System Android 16
Model Google Pixel 8 Pro
Model IDGoogle Pixel 8 Pro
Motherboard husky
Governorsched_pixel
CPU Information
Name ARM ARMv8
Topology 1 Processor, 9 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3406 revision 0
Base Frequency 1.70 GHz
Cluster 14 Cores @ 1.70 GHz
Cluster 24 Cores @ 2.37 GHz
Cluster 31 Core @ 2.91 GHz
Memory Information
Size 11.28 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 271
50.4 IPS
 
Image Classification (HP)
100% 3675
683.4 IPS
 
Image Classification (Q)
99% 7247
1.35 KIPS
 
Image Segmentation (SP)
100% 354
5.74 IPS
 
Image Segmentation (HP)
100% 7345
119.1 IPS
 
Image Segmentation (Q)
98% 15111
245.7 IPS
 
Pose Estimation (SP)
100% 428
0.50 IPS
 
Pose Estimation (HP)
100% 30685
35.8 IPS
 
Pose Estimation (Q)
97% 60851
71.3 IPS
 
Object Detection (SP)
100% 216
17.1 IPS
 
Object Detection (HP)
100% 3835
304.2 IPS
 
Object Detection (Q)
87% 4729
379.3 IPS
 
Face Detection (SP)
100% 583
6.92 IPS
 
Face Detection (HP)
100% 12894
153.2 IPS
 
Face Detection (Q)
97% 24737
294.9 IPS
 
Depth Estimation (SP)
100% 519
4.00 IPS
 
Depth Estimation (HP)
99% 32598
251.1 IPS
 
Depth Estimation (Q)
64% 30902
284.5 IPS
 
Style Transfer (SP)
100% 740
0.95 IPS
 
Style Transfer (HP)
100% 748
0.96 IPS
 
Style Transfer (Q)
72% 2979
4.09 IPS
 
Image Super-Resolution (SP)
100% 263
9.73 IPS
 
Image Super-Resolution (HP)
100% 7872
290.7 IPS
 
Image Super-Resolution (Q)
97% 12434
460.7 IPS
 
Text Classification (SP)
100% 353
471.3 IPS
 
Text Classification (HP)
100% 354
473.1 IPS
 
Text Classification (Q)
92% 1016
1.36 KIPS
 
Machine Translation (SP)
100% 560
9.65 IPS
 
Machine Translation (HP)
100% 517
8.91 IPS
 
Machine Translation (Q)
57% 347
8.47 IPS
 

Compare

Set Baseline Geekbench 6 now available